In this report, we are going to apply transfer learning techniques in order to build a deep neural net that is able to classify images of musical instruments. All images are 224 X 224 X 3 in .jpg format. The whole dataset includes almost 5000 images partitioned into 30 sub directories, one for each of the 30 types of instruments.
The problem that this model seeks to solve is a problem of classification. The environment used is MATLAB. The objective is to correctly guess the category of each musical instrument. To deal with the problem I decided to use a pre- trained CNN: GoogLeNet.